Enhanced Generic Video Summarization using Large Scale Categorization
|Priyamvada R Sachan1, Keshaveni2
|Related article at Pubmed, Scholar Google|
Over the past few years, there has been a massive increase in amount of video content created. Massive growth in video content poses problem of information overload and management of content. In order to manage the growing videos on the web and also to extract efficient and valid information from the videos, more attention has to be paid towards video and image processing technologies. Video summaries provide condensed and succinct representations of the content of a video stream through a combination of still images, video segments, graphical representations and textual descriptors. Existing video summarization techniques have attempted to solve the problem of condensing the content of a video in domain specific manner. However, such domain specific summarization mechanisms do not generalize well over different genres of videos. To make video summarization scalable enough to cater to the needs of growing massive online video content, it needs to be generic and adaptable for its applicability on any category of video. This work presents a general approach towards video summarization process and proposes a two-step approach towards domain independent generic video summarization incorporating video categorization for enhanced keyframe extraction. This paper also talks about building effective mechanisms for large scale categorization over big hierarchical category tree of videos.